Figure 5

Assessment of estimator performance by cross validation for the MAQC data sets. Average estimated prediction error for the Applied Biosystems, Affymetrix 1, and Affymetrix 2 data sets of the rat toxicogenomics subset of the MAQC study. Error and algorithm definitions are the same as those of Figure 1. Results for both Affymetrix data sets with the "fold change > 4" hard threshold estimator, the "all nulls true" estimator, and the local FDR estimator based on t statistics and the empirical null are greater than 1.7 and are not plotted.